From 9fc80780643d5a7c74b5d99b08d5def589ecb314 Mon Sep 17 00:00:00 2001 From: ssbuild <462304@qq.cn> Date: Fri, 12 May 2023 14:11:51 +0800 Subject: [PATCH] 0.1.5 Signed-off-by: ssbuild <462304@qq.cn> --- README.md | 9 +++++---- setup.py | 2 +- 2 files changed, 6 insertions(+), 5 deletions(-) diff --git a/README.md b/README.md index 04697a8c..71960bb8 100644 --- a/README.md +++ b/README.md @@ -13,14 +13,15 @@ ## state - - ppo 完善中... + - Reinforcement learning... ## update - 2023-05-10 - fix lora v2 modules_to_save 自定义额外训练模块 - - 0.1.5 rc0 增加reward ppo llm 完整训练 [llm_rlhf_training](https://github.com/ssbuild/llm_rlhf_training) - - 0.1.5 rc1 增加reward ppo chatglm 完整训练 [chatglm_rlhf_training](https://github.com/ssbuild/chatglm_rlhf_training) - - 0.1.5 rc2 增加reward ppo chatglm 完整训练 [chatyuan_rlhf_training](https://github.com/ssbuild/chatyuan_rlhf_training) + - 增加reward ppo llm 完整训练 [rlhf_llm](https://github.com/ssbuild/rlhf_llm) + - 增加reward ppo chatglm 完整训练 [rlhf_chatglm](https://github.com/ssbuild/rlhf_chatglm) + - 增加reward ppo chatyuan 完整训练 [rlhf_chatyuan](https://github.com/ssbuild/rlhf_chatyuan) + - 2023-05-02 - 0.1.4 增加 prompt_tuning,p_tuning,prefix_tuning,adaption_prompt diff --git a/setup.py b/setup.py index 59769c63..5f1c260b 100644 --- a/setup.py +++ b/setup.py @@ -5,7 +5,7 @@ ignore = ['test','tests'] setup( name='deep_training', - version='0.1.5rc2', + version='0.1.5', description='an easy training architecture', long_description='torch_training: https://github.com/ssbuild/deep_training.git', license='Apache License 2.0',